Browserbase MCP server

This MCP server provides a standardized way to connect LLMs with context through browser automation. It leverages Browserbase and Stagehand to enable AI models to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.

Installation

You can install the MCP server using Smithery:

# Install via Smithery
smithery install @browserbasehq/mcp-browserbase

Available MCP Components

Browserbase MCP

Browserbase MCP offers powerful browser automation capabilities:

• Browser automation for controlling cloud browsers
• Data extraction from any webpage
• Console monitoring for tracking browser logs
• Screenshot capture (full-page and element-specific)
• Web interaction (navigation, clicking, form filling)

Stagehand MCP

Stagehand MCP provides more granular control with:

• Atomic instructions like act("click the login button") or extract("find the red shoes")
• Support for multiple models including OpenAI's GPT-4 and Anthropic's Claude-3.7 Sonnet
• Modular design for easy integration of new models
• Vision support with annotated screenshots for complex DOMs

Usage Examples

Basic Browser Automation

// Example of using Browserbase MCP for browser automation
const browser = await browserbase.launch();
const page = await browser.newPage();
await page.goto('https://example.com');
const title = await page.title();
console.log(`Page title: ${title}`);

Data Extraction

// Extract data from a webpage
const data = await page.evaluate(() => {
  const products = Array.from(document.querySelectorAll('.product'));
  return products.map(p => ({
    name: p.querySelector('.name').textContent,
    price: p.querySelector('.price').textContent,
    description: p.querySelector('.description').textContent
  }));
});

Taking Screenshots

// Capture a full-page screenshot
await page.screenshot({ path: 'screenshot.png', fullPage: true });

// Capture a specific element
const element = await page.$('.header');
await element.screenshot({ path: 'header.png' });

Using Stagehand's Atomic Instructions

// Execute precise actions with Stagehand
await stagehand.act("click the login button");
await stagehand.extract("find the price of the red shoes");

// Using vision support
const screenshot = await page.screenshot();
const result = await stagehand.analyzeWithVision(screenshot, "What items are on sale?");

Additional Resources

For more detailed information, you can visit:

• Model Context Protocol Documentation
• Browserbase Website
• Stagehand GitHub Repository

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.